Quality Assessment of Coffee Beans Using Convolutional Neural Networks with Wavelet and CLAHE Techniques
Resumo
This paper presents an analytical study comparing different filtering techniques applied to a Convolutional Neural Network (CNN) for coffee bean classification. The results demonstrated that the CLAHE (Contrast Limited Adaptive Histogram Equalization) filter achieved the highest performance, with an accuracy of 0.8875 on the test set. The findings indicate that applying filtering techniques can enhance the performance of the ResNet18 network. CLAHE’s effectiveness is attributed to its ability to improve image details and contrast, leading to superior classification results. This study underscores the potential of advanced filtering methods to boost CNN performance in image classification tasks.
Palavras-chave:
Wavelet, CLAHE, Resnet18, Coffee Bean, CNN
Referências
MUSA, Purnawarman; AL RAFI, Farid; LAMSANI, Missa. A Review: Contrast-Limited Adaptive Histogram Equalization (CLAHE) methods to help the application of face recognition. In: 2018 Third International Conference on Informatics and Computing (ICIC). IEEE, 2018. p. 1-6.
CAVATON, Thiago Farah. (23 de janeiro de 2023). Faturamento das lavouras dos Cafés do Brasil alcança R$ 56 bilhões em 2022. Acesso em: [link]
AgroPós (agosto de 2017). Principais Doenças do Café: Diagnose e Controle! Acesso em: [link]
ESGARIO, José G. M. et al. An app to assist farmers in the identification of diseases and pests of coffee leaves using deep learning. Information Processing in Agriculture, v. 9, n. 1, p. 38-47, 2022. DOI: 10.1016/j.inpa.2021.01.004
WANI, M. A. et al. Advances in deep learning. [S.l.]: Springer, v. 57, 2020. DOI: 10.1007/978-981-13-6794-6
AWARI (5 de março de 2023) Visão computacional: o que é e como funciona esta inteligência artificial. Acesso em: [link]
WANG, Ping et al. Deep convolutional neural network for coffee bean inspection. Sensors and Materials, v. 33, n. 7, p. 2299-2310, 2021. DOI: 10.18494/SAM.2021.3277
FEBRIANA, Alifya et al. USK-COFFEE dataset: a multi-class green arabica coffee bean dataset for deep learning. In: 2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom). IEEE, 2022. p. 469-473. DOI: 10.1109/CyberneticsCom55287.2022.9865489
PRZYBYŁ, Krzysztof et al. Application of machine learning to assess the quality of food products—case study: Coffee bean. Applied Sciences, v. 13, n. 19, p. 10786, 2023. DOI: 10.3390/app131910786
ESGARIO, José G. M.; KROHLING, Renato A.; VENTURA, José A. Deep learning for classification and severity estimation of coffee leaf biotic stress. Computers and Electronics in Agriculture, v. 169, p. 105162, 2020. DOI: 10.1016/j.compag.2019.105162
ABUHAYI, Biniyam Mulugeta; MOSSA, Abdela Ahmed. Coffee disease classification using Convolutional Neural Network based on feature concatenation. Informatics in Medicine Unlocked, v. 39, p. 101245, 2023. DOI: 10.1016/j.imu.2023.101245
HE, Kaiming et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. p. 770-778.
HANG, Shyang-Jye; HUANG, Chien-Yu. Deep learning model for the inspection of coffee bean defects. Applied Sciences, v. 11, n. 17, p. 8226, 2021. DOI: 10.3390/app11178226
RONNEBERGER, Olaf; FISCHER, Philipp; BROX, Thomas. U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer International Publishing, 2015. p. 234-241. DOI: 10.1007/978-3-319-24574-4_28
ZHAO, Hengshuang et al. Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017. p. 2881-2890. DOI: 10.48550/arXiv.1612.01105
PETSI (19 de abril de 2017) Redes neurais convolucionais aplicadas à análise de gestos considerando os problemas estudados na área de Estudos dos Gestos. Acesso em: [link]
JANSEN, M. Noise reduction by wavelet thresholding. [S.l.]: Springer Science & Business Media, v. 161, 2012.
BELCIUG, S. Artificial intelligence in cancer: diagnostic to tailored treatment. Cambridge: Academic, 2020.
CAVATON, Thiago Farah. (23 de janeiro de 2023). Faturamento das lavouras dos Cafés do Brasil alcança R$ 56 bilhões em 2022. Acesso em: [link]
AgroPós (agosto de 2017). Principais Doenças do Café: Diagnose e Controle! Acesso em: [link]
ESGARIO, José G. M. et al. An app to assist farmers in the identification of diseases and pests of coffee leaves using deep learning. Information Processing in Agriculture, v. 9, n. 1, p. 38-47, 2022. DOI: 10.1016/j.inpa.2021.01.004
WANI, M. A. et al. Advances in deep learning. [S.l.]: Springer, v. 57, 2020. DOI: 10.1007/978-981-13-6794-6
AWARI (5 de março de 2023) Visão computacional: o que é e como funciona esta inteligência artificial. Acesso em: [link]
WANG, Ping et al. Deep convolutional neural network for coffee bean inspection. Sensors and Materials, v. 33, n. 7, p. 2299-2310, 2021. DOI: 10.18494/SAM.2021.3277
FEBRIANA, Alifya et al. USK-COFFEE dataset: a multi-class green arabica coffee bean dataset for deep learning. In: 2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom). IEEE, 2022. p. 469-473. DOI: 10.1109/CyberneticsCom55287.2022.9865489
PRZYBYŁ, Krzysztof et al. Application of machine learning to assess the quality of food products—case study: Coffee bean. Applied Sciences, v. 13, n. 19, p. 10786, 2023. DOI: 10.3390/app131910786
ESGARIO, José G. M.; KROHLING, Renato A.; VENTURA, José A. Deep learning for classification and severity estimation of coffee leaf biotic stress. Computers and Electronics in Agriculture, v. 169, p. 105162, 2020. DOI: 10.1016/j.compag.2019.105162
ABUHAYI, Biniyam Mulugeta; MOSSA, Abdela Ahmed. Coffee disease classification using Convolutional Neural Network based on feature concatenation. Informatics in Medicine Unlocked, v. 39, p. 101245, 2023. DOI: 10.1016/j.imu.2023.101245
HE, Kaiming et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016. p. 770-778.
HANG, Shyang-Jye; HUANG, Chien-Yu. Deep learning model for the inspection of coffee bean defects. Applied Sciences, v. 11, n. 17, p. 8226, 2021. DOI: 10.3390/app11178226
RONNEBERGER, Olaf; FISCHER, Philipp; BROX, Thomas. U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer International Publishing, 2015. p. 234-241. DOI: 10.1007/978-3-319-24574-4_28
ZHAO, Hengshuang et al. Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017. p. 2881-2890. DOI: 10.48550/arXiv.1612.01105
PETSI (19 de abril de 2017) Redes neurais convolucionais aplicadas à análise de gestos considerando os problemas estudados na área de Estudos dos Gestos. Acesso em: [link]
JANSEN, M. Noise reduction by wavelet thresholding. [S.l.]: Springer Science & Business Media, v. 161, 2012.
BELCIUG, S. Artificial intelligence in cancer: diagnostic to tailored treatment. Cambridge: Academic, 2020.
Publicado
06/11/2024
Como Citar
REIS, Marcus Vinicius Diniz dos; SOUSA, Pedro Moises de.
Quality Assessment of Coffee Beans Using Convolutional Neural Networks with Wavelet and CLAHE Techniques. In: WORKSHOP DE SISTEMAS DE INFORMAÇÃO (WSIS), 15. , 2024, Rio Paranaíba/MG.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2024
.
p. 33-38.
DOI: https://doi.org/10.5753/wsis.2024.33669.
